Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 36 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1249. Min Range: -3.1249

Max Act: 3.1249. Min Act: -0.1700

Data Index: 814806 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 3.1249. Min Range: -3.1249

Max Act: 3.0776. Min Act: -0.1700

Data Index: 1248934 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 3.1249. Min Range: -3.1249

Max Act: 3.0461. Min Act: -0.1700

Data Index: 1299983 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 3.1249. Min Range: -3.1249

Max Act: 3.0776. Min Act: -0.1700

Data Index: 1885 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 3.1249. Min Range: -3.1249

Max Act: 3.0619. Min Act: -0.1700

Data Index: 1267108 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 3.1249. Min Range: -3.1249

Max Act: 3.0776. Min Act: -0.1700

Data Index: 290630 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 3.1249. Min Range: -3.1249

Max Act: 2.9987. Min Act: -0.1700

Data Index: 870026 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 3.1249. Min Range: -3.1249

Max Act: 3.0619. Min Act: -0.1700

Data Index: 941582 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 3.1249. Min Range: -3.1249

Max Act: 3.0303. Min Act: -0.1700

Data Index: 27177 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 3.1249. Min Range: -3.1249

Max Act: 3.0776. Min Act: -0.1700

Data Index: 136201 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 3.1249. Min Range: -3.1249

Max Act: 2.9987. Min Act: -0.1700

Data Index: 134930 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 3.1249. Min Range: -3.1249

Max Act: 3.0303. Min Act: -0.1700

Data Index: 1196798 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 3.1249. Min Range: -3.1249

Max Act: 3.0303. Min Act: -0.1700

Data Index: 132030 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 3.1249. Min Range: -3.1249

Max Act: 3.0145. Min Act: -0.1700

Data Index: 710000 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 3.1249. Min Range: -3.1249

Max Act: 3.0145. Min Act: -0.1700

Data Index: 75467 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 3.1249. Min Range: -3.1249

Max Act: 2.9987. Min Act: -0.1700

Data Index: 370513 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 3.1249. Min Range: -3.1249

Max Act: 3.0303. Min Act: -0.1700

Data Index: 26934 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 3.1249. Min Range: -3.1249

Max Act: 2.9829. Min Act: -0.1700

Data Index: 966413 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 3.1249. Min Range: -3.1249

Max Act: 3.0145. Min Act: -0.1700

Data Index: 205607 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 3.1249. Min Range: -3.1249

Max Act: 3.0145. Min Act: -0.1700

Data Index: 1142675 (C4 (Web Text))

Max Activating Token Index: 220